© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54239
    Prev
    Next
    INDEX
    Explanations

    // characters and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    -0.11
    edu
    -0.07
    oftware
    -0.07
    edral
    -0.07
     Panther
    -0.07
    sts
    -0.06
     dirty
    -0.06
     Dirty
    -0.06
     cleaner
    -0.06
    ies
    -0.06
    POSITIVE LOGITS
    ally
    0.14
    opsis
    0.11
    ply
    0.11
    leur
    0.11
    ALLY
    0.11
    urge
    0.10
    atro
    0.10
    ical
    0.10
     cris
    0.10
    ley
    0.10
    Activations Density 0.012%

    No Known Activations